© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130553
    Prev
    Next
    INDEX
    Explanations

    six, four, five, paired

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tiny
    -0.07
    ↵
    -0.07
     the
    -0.07
     अन्यथा
    -0.06
     chosen
    -0.06
    以便
    -0.06
    מע
    -0.06
    tiny
    -0.06
     Sudden
    -0.06
     bạch
    -0.06
    POSITIVE LOGITS
     могут
    0.07
    最重要的
    0.07
     даже
    0.07
     can
    0.06
     شاید
    0.06
    多くの
    0.06
    вЂ
    0.06
     थिएटर
    0.06
     thậm
    0.06
    郢
    0.06
    Activations Density 0.004%

    No Known Activations